Evaluation of physician performance using a concurrent-read artificial intelligence system to support breast ultrasound interpretation.

PURPOSE: The purpose of this study was to compare the diagnostic performance and the interpretation time of breast ultrasound examination between reading without and with the artificial intelligence (AI) system as a concurrent reading aid. MATERIAL AND METHODS: A fully crossed multi-reader and multi-case (MRMC) reader study was conducted. Sixteen participating physicians were recruited and retrospectively interpreted 172 breast ultrasound cases in two reading scenarios, once without and once with the AI system (BU-CAD™, TaiHao Medical Inc.) assistance for concurrent reading. Interpretations of any given case set with and without the AI system were separated by at least 5 weeks. These reading results were compared to the reference standard and the area under the LROC curve (AUCLROC), sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) were calculated for performance evaluations. The interpretation time was also compared between the unaided and aided scenarios. RESULTS: With the help of the AI system, the readers had higher diagnostic performance with an increase in the average AUCLROC from 0.7582 to 0.8294 with statistically significant. The sensitivity, specificity, PPV, and NPV were also improved from 95.77%, 24.07%, 44.18%, and 93.50%-98.17%, 30.67%, 46.91%, and 96.10%, respectively. Of these, the improvement in specificity reached statistical significance. The average interpretation time was significantly reduced by approximately 40% when the readers were assisted by the AI system. CONCLUSION: The concurrent-read AI system improves the diagnostic performance in detecting and diagnosing breast lesions on breast ultrasound images. In addition, the interpretation time is effectively reduced for the interpreting physicians.

Therapeutic evaluation of HIV transduction basic domain-conjugated superoxide dismutase solution on suppressive effects of the formation of peroxynitrite and expression of COX-2 in murine skin.

BACKGROUND: Homeostasis of reactive oxygen species (ROS) in the skin is regulated by antioxidant defenses. The inflammatory states of skin diseases which range from acute rashes to chronic conditions are related to the level of ROS. The involvement of superoxide dismutase (SOD) in restoring the antioxidant capacity can then neutralize the inflammatory response. RESULTS: We found that denatured Tat-SOD formulated in an aqueous medium could be delivered into mouse skin and the penetration signals of Tat-SOD were detected in the epidermis and dermis. According to immunohistochemical staining, Tat-SOD successfully suppressed inflammation induced by 12-O-tetradecanoylphorbol-13-acetate (TPA), the expression of sodium nitroferricyanide (SNP)-induced cyclooxygenase-2 (COX-2), and the production of nitrotyrosine proteins. In nerve growth factor (NGF) induced differentiated PC12 pheochromocytoma cells, we demonstrated that the denatured Tat-SOD regained its antioxidant activity and effectively protected PC12 cells from DNA fragmentation induced by paraquat. Using a luciferase reporter assay, the data was shown Tat-SOD protected PC12 cells from ROS damage, through suppression of COX-2 or nuclear factor-κB (NF-κB) activity occurred at the transcriptional level. CONCLUSION: We showed that Tat-SOD inhibited SNP-induced COX-2 expression similarly to celecoxib and prevented the formation of peroxynitrite as 2-phenyl-4,4,5,5-tetramethylimidazoline-1-oxyl-3-oxide. The results suggest that denatured Tat-SOD solution may perform potential protein therapy for patients suffering from disorders related to ROS.